An Empirical Study of MPI over PC Clusters

Size: px
Start display at page:

Download "An Empirical Study of MPI over PC Clusters"

Transcription

1 An mpirical Sudy of MPI over PC Clusers Fazal Noor*, Majed Alhaisoni*, Anonio Lioa+ *Compuer Science and Sofware ngineering Deparmen Universiy of Hail, Saudi Arabia +Deparmen of lecrical ngineering and Deparmen of Mahemaics and Compuer Science Technische Universiei indhoven The Neherlands Absrac Message Passing Inerface (MPI) is an imporan mechanism in P2P. Herein we assess how differen ypes of MPI collecive communicaion funcions perform on a Gigabi herne Homogeneous Beowulf PC cluser. In his way we provide an insigh on he facors ha affec P2P applicaions over an enerprise conex such as he emerging Cloud-based services. By conras o he lieraure, which includes mosly heoreical sudies, we carry ou an empirical sudy. We show ha he bahaviour of scaer and gaher are mos unpredicable in comparison wih oher collecive funcions. Keywords - MPI benchmark, Homogeneous PC Cluser, herne, Collecive Communicaions, Laency, Bandwidh, Allo-all, Gaher, Scaer, Broadcas. I. INTRODUCTION In recen years Peer-o-Peer (P2P) neworks have become an acive area of research [1]-[4]. Tradiional neworks use he clien/server paradigm where dedicaed servers offer cliens services. P2P neworks are characerized by all peers having he capabiliy of boh being a clien and a server. P2P neworks can suppor many applicaions such as sharing of resources, e.g. communicaion services, file sharing, query search, disribued compuing, ec. In P2P opology, MPI (Message Passing Inerface) is considered as a common communicaion proocol for various P2P sysems. Therefore, i is considered as a good mechanism wih is goals are o have high performance, scalabiliy, and porabiliy. Having low delay wih reasonable hroughpu is imporan for compuing clusers, due o a lack of shared memory implies large amouns of nework daa ransfer. However, porabliliy is very imporan for MPI. The scalabiliy of MPI is mainly due o MPI being he real sandard in disribued compuing. In his paper, a simulaion of P2P is done using MPI collecive communicaions rouines on a PC cluser o measure and evaluae he performance of P2P sysem. A homogeneous PC cluser is defined as one having idenical hardware (including nework hardware such as swiches) and operaing sysem on all he machines in he nework. I is considered heerogeneous if PC hardware and/or sofware is differen from each oher in a cluser. One of he reasons o sudy homogeneous PC cluser is o gain insigh ino he behaviour of collecive communicaion models used as models usually are made under he assumpion of homogeneiy. The objecive of his paper is wofold, firs o sudy how a variey of MPI communicaion models perform over PC clusers. Second, we define and measure in pracical seings he execuion ime of herne neworks. We pinpoin he overheads and how hese affec link efficiency. Among all echnologies, including Infiniband [5], Quadrics [6], and Myrine [7], we have decided o focus on herne which is readily available for experimenaion. The paper is organized as follows, in Secion II some relaed work is presened. In Secion III experimenal mehods are presened and in Secion IV he resuls are presened. Secion V conains discussion of he resuls presened. Finally in Secion VI conclusion and fuure work is presened. II. RLATD WORK There has been a lo of work on MPI communicaions performance of PC cluser. Mos of work is performed on a heerogeneous Beowulf PC clusers. In our work we focus on sudying he performance of MPI collecive communicaions on homogeneous Beowulf PC cluser consising of 20 idenical machines. In [9] he auhors have used MPIBench a sofware for benchmarking he performance of MPI funcions using a highly accurae, globally synchronized clock. In [10] he auhors have developed a MagPIe library which opimizes MPI s collecive communicaion and have used a LogP model for shor messages and LogGP model for long messages (Table 1). In [11] a nice comparison is made among he common 65

2 parallel communicaon models appearing in he vas lieraure, such as Hockney, LogP, LogGP, and PlogP. All hese models appearing in he lieraure make an assumpion of a homogeneous environmen and are lised in Table 1 [11]. Table 1: Common Communicaion Models Model Time Parameers Hockney Log P Log GP P Log P T = l + m/b T= o + ( k/w -1)*max (g,o) + L + o T= o + (k-1)g + L + o Same as Log P bu wih each parameer being dependen on message size. l : is laency of nework b: is bandwidh o: overhead ime o ransmi or receive g: gap min ime inerval beween message p: number of processors l: upper bound on laency k: number of byes in a message w: size of he nework package in byes G: gap per bye for long messages Same as Log P bu dependan on message lengh m L: end o end laency However analyical models can no ruly replace acual performance measuremens. In our work we presen empirical resuls of he MPI collecive communicaion rouines. Such funcions provide insigh o communicaing on boh wireless and wired Peer-o-Peer sysems. III. XPRIMNTAL MTHODS A. Performance Measuremen The facors which affec performance are many and may be lised as: 1. Hardware relaed: CPU clock speed and number of CPUs on moherboard, memory, and nework adapers. 2. Nework relaed: Type of hardware, cable, faseherne, swiches, and rouers. Proocols used TCP/IP, UDP/IP and ohers. 3. Sofware relaed: Operaing sysem ype, user buffering, kernel buffering of daa, ypes of MPI rouines used for example collecive communicaions. MPI eager and rendezvous proocols, efficiency of algorihms, and polling or inerrups. From he above we can define execuion ime as a funcion of boh hardware and sofware. xecuion Time will be a funcion of opology, number of nodes, message size, swich, rouer, nework adaper, ype of algorihm, link ype, overhead compuer and operaing sysems, physical medium, MPI relaed, TCP/IP relaed, and herne relaed. This is indeed a very complex funcion in which laencies of boh hardware and sofware have o be considered. Hard disk, RAM, and cache access imes wih nework inerface card, PCI, and PCI xpress ransporaion imes need o be considered in calculaion of execuion ime. Also he laencies of nework devices should be considered such as he swiches which are in he 2 o 20 µsec range [8]. In rouers he processing delay due o sofware processes would be considerably higher. DSL or Cable inerne connecions have less han 100 milliseconds (ms) delays bu less han 25 ms are desired. Saellie Inerne connecions have an average of 500 ms or higher laency. The peak heoreical bandwidh of a nework connecion is fixed by he echnology used bu he acual hroughpu (bandwidh) varies wih ime and is affeced by high laencies. xcessive laencies on he nework causes bolenecks ha hinder flow of daa herefore decreasing effecive bandwidh. The oal ime of sending a message from one peer o anoher peer compuer can be represened in erms of execuion imes and communicaion ime as, Time = + +, (1) execa comm where exec ime can be defined as, execb exec = K C / f. (2) where K is insrucions per program, C is clock cycles per insrucion and f is CPU frequency. The ime involves he message s journey from he ransmiing compuer s memory, user space o kernel space o he nework inerface, hrough he physical medium, o he swich, and hen o he receiver compuer s nework inerface, and up o he applicaion. In Peer-o-Peer applicaions collecive operaions are rampan. Broadcas, scaer, and gaher rouines are common and heir communicaion ime depends on he size of each message, number of messages, inerconnecion srucure, and nework conenion. The communicaion ime can be wrien as comm = s + m + c. (3) In he above equaion s is he message laency assumed consan and includes he overhead ime a he source and desinaion; is he ransmission ime compued as 1/B where B is link bandwidh given in Q bis/sec; and m represens message o send. The conenion ime c is burs dependen and usually removed for simpliciy. The ime complexiy is O(m) for m daa iems. Usually one sends messages from one compuer o muliple desinaions. The 1-o-N fan-ou broadcas is when he same message is sen o N desinaions sequenially, hen he communicaion ime is 66

3 comm = N( s + m ), (4) and for he scaer and gaher communicaion models is, comm = N( s + m / n). (5) In scaer a unique message is sen from source o every oher desinaion and in gaher a unique message is received from every oher nodes. The ime complexiy is O (Nm) for one source connecing o N desinaions. In (5), n is he oal number of nodes and N = n-1. For a ree ype srucure he ime complexiy of 1-o-N fan-ou will depend on number of nodes a each level and he number of levels. The disadvanage of a binary ree implemenaion is if one node fails hen all he nodes below i will no receive he message. For an herne LAN nework, communicaion ime can be defined as: = + m (6) comm m where all erms depend on message size and message ime a Media Access Conrol (MAC); m is dependan on message size and would be same for a homogeneous nework and would be some facor muliplied by message size, α msize ; m represens he number of bis in an herne packe; q is he queuing delay; p is he propagaion delay defined as d/c, where d is he lengh of he link and c is speed of ligh in medium having a value 8 less han 3x10 m/sec (e.g. Copper wire.77c); is he herne inerframe gap which is 12 byes (96 bis). The raffic inensiy can be defined as T q ( m p) p i / B = (7) where p is he average packe arrival rae. Therefore T i approaching close o 0 will indicae small delay; Ti approaching o 1 is an indicaion of large delay. The communicaion overhead can affec ransmission efficiency. The ransmied herne packe has a payload which is TCP/IP encapsulaed in addiion o he applicaion header. TCP header consiss of 20 byes and he IP header consiss of a leas 20 byes. The ransmied herne frame has a preamble of 8 byes and an inerframe gap of 12 byes. The number of herne packes per second on he link will be, hernepackespersecond = B / [ 8 *(FrameSize + Inerframe gap 12 byes + Preamble 8 byes ) ] (8) The herne proocol efficiency is defined as, fficiency = Payload size/ Frame size (9) and he hroughpu is Throughpu = fficiency x B (10) Therefore for every herne packe on he link, a 96 bi inerframe gap and 64 bis of preamble would be overhead. If he link has he capaciy of 1 Gbps hen for a minimum herne frame size of 64 byes ransmied, he link will consis of 7.62 x 10^8 bis/sec due o herne frame and an overhead of 2.38 x 10^8 bis/sec due o inerframe gap and preamble combined. For a Gigabi herne he minimum frame size would be 512 byes when operaing in halfduplex mode. The herne proocol efficiency is low for small packes (e.g % for 64 byes) and high (e.g % for 1518 byes) for large packes and hence he hroughpu is low for small packes and high for large packes. Laency can have derimenal affecs lasing few seconds or can be persisen depending on source of delays. Boh bandwidh and laency are wo main eniies o measure nework performance. Since sofware relaed laencies are hard o measure and define, one resors o empirical mehods as done in he nex secion. B. Beowulf PC cluser Specificaions Our esbed consiss of a PC cluser including 20 Lenovo machines wih he following specificaions: Inel Core 2 Duo CPU, GHz, 1.00 GB of RAM. Nework Card: Broadcom Nelink, Gigabi herne, Driver dae 8/28/2006 version The PC are conneced o a Gigabi D-Link herne swich. ach machine has RedHa nerprise AS Linux operaing sysem insalled, and use LAM 7.0.6/MPI 2. C. MPI Benchmarks The Message Passing Inerface (MPI) is a sandard inerface ha is broadly used wih disribued compuing applicaions [12]-[15]. The following MPI-based benchmarks are used o es he communicaion performance of he nodes: a) All-o-all: every node sends a message o every oher node. b) Broadcas: one node sends one message o every oher node. c) Gaher: all nodes send a differen message o a single node. d) Scaer: a single node sends a differen message o every oher node. e) Poin-o-Poin: a single message is sen/received beween 2 specific nodes. The implemenaion deails of he above collecive communicaions are usually unknown o he programmer. 67

4 The MP1-1 sandard specified he blocking collecive communicaions only while he MPI-2 sandard defines non-blocking rouines which perform beer wih some applicaions. MPI relaed sofware performance will depend on he ype of message passing proocols, eager (asynchronous communicaion) or rendezvous (synchronous), ype of message buffering (user and sysem), sender-receiver synchronizaion (e.g. polling or inerrup), and efficiency of he algorihms used o implemen he collecive communicaion rouines. There are many benchmarking sofware available on he inerne such as MPIBench or mppes. However, mos benchmarks available for collecive communicaion basically use he following procedure o measure he execuion ime. 1. All processes arrive a Barrier 2. Sar ime 3. MPI_collecive_fn 4. All processes arrive a Barrier 5. nd ime 6. PTime = nd_ ime Sar_ime where MPI_collecive_fn is one of he MPI funcions all-oall, gaher, scaer, broadcas, and Poin-o-Poin. D. Analysis of xecuion Time (PTime) In he benchmark procedure above, PTime consiss of ime o execue he MPI_collecive_fn funcion and wice he ime of Barrier. Firs, he ime spen a he ransmiing compuer would involve sending daa by he kernel of sysem o he nework inerface card (NIC) and he ime NIC akes o pack byes in an herne frame o send he frame on he physical wire. Depending on ype of NIC archiecure, a ypical herne NIC would have specificaions as given in Table 2. Table 2. Gigabi herne Nework Inerface Specificaions. Speed Inerface Daa Widh Clock Time for 1 bye ransfer 1 Gbps GMII 8 bis 125 MHz 8 ns 10 Gbps XGMII 32 bis MHz.8 ns To ransmi an herne frame he ime o ransmi from Medium Access Conrol (MAC) o Physical (PHY) for a 1 Gbps link would be T = 8 ns * herne_frame_size (10) One hing abou Gigabi herne is is clock rae a 125 MHz bu more daa is ransmied per ime. The ransfer rae is higher since 125 MHz x 2 bis per signal (i.e. per wire pair in Ca 5 cable) x 4 signals per ime = 1 Gbps. Therefore, on he moherboard if PCI xpress is available hen wih a maximum ransfer rae of up o 250 MB/s hen full speed of Gigabi herne is achievable. Nex, he swich receives he herne frame, and processes he frame wih a ypical delay of 2 o 20 µsecs [8]. I is hen sen ou o he desinaion compuer where again he NIC on receiving compuer processes i (PHY aking anywhere from 200 o 300 nanoseconds depending on echnology) and sends i o he MAC layer, hen ono he TCP/IP layers up o he applicaion. The process of ransmiance, recepion, and acknowledgemen is repeaed according o TCP/IP, herne framing, and depending upon he applicaion s insrucions, i.e. MPI collecive_fn funcion and ime of Barrier. The Barrier is used o explicily conrol he flow of execuion. There are a leas 3 ypes of Barrier implemenaions [9], namely, a) Couner implemenaion (linear barrier) b) Tree implemenaion c) Buerfly barrier The ime complexiy of barrier wih couner implemenaion is O (n). For boh he ree and he buerfly implemenaions he ime complexiy is O (log n), where n is he number of nodes. From he above, PTime depends on how MPI collecive_fn and Barrier are implemened in LAM 7.0.6/MPI 2, as summarized in Table 3 (for large number of nodes). Table 3. Time Complexiy Linear Model PTime Barrier Implemenaion a) Couner b) Tree and c) Buerfly MPI_alloall O(nNm) + O(n) O(nNm) + O(log n) MPI_Bcas O(Nm) + O(n) O(Nm) + O(log n) MPI_Gaher O(Nm) + O(n) O(Nm) + O(log n) MPI_Scaer O(Nm) + O(n) O(Nm) + O(log n) IV. RSULTS The MPI benchmarks are run on a PC cluser by firs fixing he number of nodes in a communicaion group o 2 and varying he size of messages from x Kbyes o y Mbyes n ( 2 where n = 0,1,2,3,4,). Then he number of nodes in communicaion group is ieraively incremened up o 20 nodes. The figures show Minimum Round Trip (MRT) ime measured in granulariy of µsecs for messages of sizes ranging from 256 KB o 2 MB. In Figure 1 all-o-all minimum round rip ime is ploed versus number of nodes in a PC cluser. Fig. 1 show MRT is almos consan (wih lile variaion) for a communicaion group consising of anywhere from 2 o 9 nodes in comparison wih 10 o 20 nodes which shows MRT linearly increasing. In Figure 2, broadcas MRT ime is ploed versus number of nodes. From he figure we observe MRT increases wih increase in he number of nodes again wih a seeper slope for large message sizes wihin each group. Noe, from he figure i shows somewha a sep wise incremen in MRT values. 68

5 In Figures 3 and 4, gaher and scaer MRT ime is ploed versus number of nodes, respecively. Boh gaher and scaer have a similar shape for MRT. The shape is more pronounced for large message sizes wihin each group. For gaher and scaer communicaions i is seen from he figures MRT for small number of nodes e.g. 2, 3 and for large number of nodes, e.g akes on values which are much larger han he MRT of he number of nodes in beween. MRT akes on a minimum for 8, 9 nodes and slighly higher for 10 nodes. I is also ineresing o noe ha skewed shape flaens ou as he message size is reduced. The figures of scaer and gaher show unexpeced behavior in MRT for nodes up o 9. The reason for his is presened under he discussion secion. In Figure 5, Poin-o-Poin benchmark is ploed wih logarihmic scale for MRT and messages sizes ranging from 4 byes o 8 Mbyes. Comparing all-o-all communicaion wih he ohers i is seen all-o-all has he highes MRT as expeced. Figure 3. Gaher benchmark showing MRT for message sizes of 256KB, 512KB, 1MB, 2MB and for differen size of PC cluser. Figure 4. Scaer benchmark showing MRT for message sizes of 256KB, 512KB, 1MB, 2MB and for differen size of PC cluser Figure 1. All-o-all benchmark showing MRT for message sizes of 256K B, 512KB, 1MB, 2MBand for differen size of PC cluser. Figure 2. Broadcas benchmark showing MRT for message sizes of 256KB, 512KB, 1MB and for differen size of PC cluser. Figure 5. Poin-o poin benchmark showing MRT log scale versus message sizes of 4 byes o 8 Mbyes. V. DISCUSSION In his secion we discuss he resuls of all-o-all, broadcas, gaher, scaer, and Poin-o-Poin funcions used in he benchmarks. Firs noe, he message size being ransmied is fixed in he case of broadcas and Poin-o- Poin. In he second case of all-o-all, gaher, and scaer, he message size is divided equally wihin he communicaion group and depends on he number of paricipaing nodes. Le m denoe he message size and n denoe he number of nodes, s i = m / n i for i = 2,3,..., 20 (11) where s i is he acual message size being ransmied or received by each communicaing node. Therefore, s 1 > s2 > s3 L > s20 since n i < n i+ 1. As he number of nodes are increased he message size being sen or received goes down. From (5) one knows ha laency depends on message size (and of course is a funcion of ime): as he message size s i+ 1 is less han s i herefore he per message laency of s i is larger han s i+ 1. However his is no always he case as seen in he scaer and gaher rouines. When a hos applicaion ransmis o is desinaion, non-blocking sends are posed by MPI, 69

6 reducing laency for cerain nodes (e.g. 9 in he scaer figure) and he TCP proocol is used for reliabiliy. I mus wai for a period of ime o receive an acknowledgmen. If he reply does no arrive wihin he expeced period he daa is reransmied. On herne LAN he wai ime is no more han a few µsecs. Thus, he overhead ime has a major affec on laency. A number of facors ogeher are involved in having a major affec on MRT as shown in he scaer and gaher plos. Firs, varying he size of he message has affec. Second, he implemenaion of LAM-MPI rouines are no known o he programmer, which model is being used wheher linear or ree ype. Third, which proocol MPI is using eiher eager or rendezvous proocols. The LAM-MPI consrucs he message and sends i hrough he nework o he desinaion compuer which mus accep and ac upon he message conens. LAM-MPI uses eiher he eager proocol or he rendezvous proocol depending on message size. Wih he eager proocol, as soon as a message is posed boh he envelope and daa are sen o he desinaion. If on he desinaion he receive operaion is no posed hen buffering has o be done; his buffering involves an addiional daa duplicaion. In he rendezvous proocol, when a message is posed he envelope is sen o he desinaion and buffered. As soon as a receive is posed he desinaion sends an acknowledgemen o he sender which hen only will be he daa send by he sender In his case buffering of he daa is avoided and used for large messages. Fourh, TCP/IP proocol is being used by LAM-MPI proocols on op of TCP/IP proocols which cause higher laencies in communicaing a message from sender o desinaion. The acual applicaion byes packed in an herne frame are much less due o MPI applicaion, TCP/IP, and herne headers. In some cases, as depiced in he figures of scaer and gaher, when he message size decreases among he communicaion nodes i can happen ha MRT decrease down o a cerain value and, as he message size is furher decreased beyond he minimum MRT poin, he MRT will sar o increase again. The explanaion of such a behavior is due o he facors menioned above (i.e. he implemenaion of he scaer and gaher algorihms in MPI, eager and rendezvous proocol swiching depending on message size, plus TCP overhead and he increase of overhead raio as he herne frame size decreases). VI. CONCLUSION AND FUTUR WORK In his paper we have sudied he performance of MPI collecive communicaions rouines on a gigabi herne LAN. The experimens were performed o represen a Peero-Peer scenario in which one has differen sizes of nodes in a group and variaions in message size. All he benchmark rouines presened closely represen ypical communicaions of a Peer-o-Peer sysem i.e. broadcasing, gahering, scaering, all-o-all, and poin-o-poin. The resuls show in he case of gaher and scaer ha as he message size is decreased among he increasing nodes here is no se predicable paern MRT akes. We have seen ha many facors affec he performance of collecive communicaions in a wireline (herne) environmen. Our nex arge is o exend our sudy o he area of Peer-o-Peer over wireless neworks. ACKNOWLDGMNT The auhors would like o hank CSS Research Cener for carrying ou experimens on he PC cluser. The auhors would also hank he anonymous reviewers for heir valuable and insighful commens. RFRNCS [1] S. Lin, A. Pan, R. Guo, and Z. Zhang., Simulaing Large- Scale Peer-TO-Peer Sysems wih WiDS Toolki, Whie Paper, Microsof, Jan [2] M. Li, W. Lee, and A. Sivasubramaniam, fficien Peer-o- Peer Informaion Sharing over Mobile Ad Hoc Neworks, In MobA, [3] X. M. Huang, C.Y. Chang, and M.S. Chen, PeerCluser: A Cluser Based Peer-o-Peer Syem, I Transacions on Parallel and Disribued Sysems, vol. 17, No. 10, Oc. 2006, pp [4] B. Parviz and K. Miremadi, Building a Peer o Peer Message Passing nvironmen by Uilizing Reflecion in.nt., In Proceedings of PDPTA'2006. pp.1096~1102. [5] InfiniBand Trade Organizaion., hp:// [6] hp://en.wikipedia.org/wiki/quadrics, Sep. 3, [7] Myricom Inc., hp:// Sep 3, [8] CISCO Inc., hp:// Sep 3, [9] F. A. Vaughan, D. A. Grove, and P. D. Coddingon, Communiaion Issues for Two Cluser Compuers, ACSC 03 Proceedings of he 26 h Ausrailasian compuer science conference, vol 16, [10] T. Kielmann and H.. Bal, Fas Measurmen of LogP Parameers for Message Passing Plaforms, 4h Workshop on Runime Sysems for Parallel Programming (RTSPP), pp , held in conjuncion wih IPDPS 2000, Cancun, Mexico, May 1-5, Lecure Noes in Compuer Science, Vol [11] J. P. Grbovic, e al, Performance Analysis of MPI Collecive Operaions, Journal Cluser Compuing, Vol 10, Issue 2, June 2007, pp [12] R. Riesen, Communicaon Paerns, Parallel and Disribued Processing Symposium, April [13] A. Leko, e al, Pracical xperiences wih Modern Parallel Performance Analysis Tools : An valuaion, Parallel and Disribued Processing, IPDPS 2008 I Symposium April 2008, Miami, Fl, pp [14] B. Wilkinson and M. Allen, Parallel Programming Techniques and Applicaions Using Neworked Worksaions and Parallel Compuers, Second diion, Pearson Prenice Hall, [15] F. Noor and S. Misbahuddin, Using MPI on PC Cluser o Compue igenvalues of Hermiian Toepliz Marices, Lecure Noes in Compuer Science, 2010, vol 6081, pp

COSC 3213: Computer Networks I Chapter 6 Handout # 7

COSC 3213: Computer Networks I Chapter 6 Handout # 7 COSC 3213: Compuer Neworks I Chaper 6 Handou # 7 Insrucor: Dr. Marvin Mandelbaum Deparmen of Compuer Science York Universiy F05 Secion A Medium Access Conrol (MAC) Topics: 1. Muliple Access Communicaions:

More information

Assignment 2. Due Monday Feb. 12, 10:00pm.

Assignment 2. Due Monday Feb. 12, 10:00pm. Faculy of rs and Science Universiy of Torono CSC 358 - Inroducion o Compuer Neworks, Winer 218, LEC11 ssignmen 2 Due Monday Feb. 12, 1:pm. 1 Quesion 1 (2 Poins): Go-ack n RQ In his quesion, we review how

More information

Less Pessimistic Worst-Case Delay Analysis for Packet-Switched Networks

Less Pessimistic Worst-Case Delay Analysis for Packet-Switched Networks Less Pessimisic Wors-Case Delay Analysis for Packe-Swiched Neworks Maias Wecksén Cenre for Research on Embedded Sysems P O Box 823 SE-31 18 Halmsad maias.wecksen@hh.se Magnus Jonsson Cenre for Research

More information

MOBILE COMPUTING. Wi-Fi 9/20/15. CSE 40814/60814 Fall Wi-Fi:

MOBILE COMPUTING. Wi-Fi 9/20/15. CSE 40814/60814 Fall Wi-Fi: MOBILE COMPUTING CSE 40814/60814 Fall 2015 Wi-Fi Wi-Fi: name is NOT an abbreviaion play on Hi-Fi (high fideliy) Wireless Local Area Nework (WLAN) echnology WLAN and Wi-Fi ofen used synonymous Typically

More information

MOBILE COMPUTING 3/18/18. Wi-Fi IEEE. CSE 40814/60814 Spring 2018

MOBILE COMPUTING 3/18/18. Wi-Fi IEEE. CSE 40814/60814 Spring 2018 MOBILE COMPUTING CSE 40814/60814 Spring 2018 Wi-Fi Wi-Fi: name is NOT an abbreviaion play on Hi-Fi (high fideliy) Wireless Local Area Nework (WLAN) echnology WLAN and Wi-Fi ofen used synonymous Typically

More information

FIELD PROGRAMMABLE GATE ARRAY (FPGA) AS A NEW APPROACH TO IMPLEMENT THE CHAOTIC GENERATORS

FIELD PROGRAMMABLE GATE ARRAY (FPGA) AS A NEW APPROACH TO IMPLEMENT THE CHAOTIC GENERATORS FIELD PROGRAMMABLE GATE ARRAY (FPGA) AS A NEW APPROACH TO IMPLEMENT THE CHAOTIC GENERATORS Mohammed A. Aseeri and M. I. Sobhy Deparmen of Elecronics, The Universiy of Ken a Canerbury Canerbury, Ken, CT2

More information

Simple Network Management Based on PHP and SNMP

Simple Network Management Based on PHP and SNMP Simple Nework Managemen Based on PHP and SNMP Krasimir Trichkov, Elisavea Trichkova bsrac: This paper aims o presen simple mehod for nework managemen based on SNMP - managemen of Cisco rouer. The paper

More information

PART 1 REFERENCE INFORMATION CONTROL DATA 6400 SYSTEMS CENTRAL PROCESSOR MONITOR

PART 1 REFERENCE INFORMATION CONTROL DATA 6400 SYSTEMS CENTRAL PROCESSOR MONITOR . ~ PART 1 c 0 \,).,,.,, REFERENCE NFORMATON CONTROL DATA 6400 SYSTEMS CENTRAL PROCESSOR MONTOR n CONTROL DATA 6400 Compuer Sysems, sysem funcions are normally handled by he Monior locaed in a Peripheral

More information

Coded Caching with Multiple File Requests

Coded Caching with Multiple File Requests Coded Caching wih Muliple File Requess Yi-Peng Wei Sennur Ulukus Deparmen of Elecrical and Compuer Engineering Universiy of Maryland College Park, MD 20742 ypwei@umd.edu ulukus@umd.edu Absrac We sudy a

More information

4 Error Control. 4.1 Issues with Reliable Protocols

4 Error Control. 4.1 Issues with Reliable Protocols 4 Error Conrol Jus abou all communicaion sysems aemp o ensure ha he daa ges o he oher end of he link wihou errors. Since i s impossible o build an error-free physical layer (alhough some shor links can

More information

Chapter 3 MEDIA ACCESS CONTROL

Chapter 3 MEDIA ACCESS CONTROL Chaper 3 MEDIA ACCESS CONTROL Overview Moivaion SDMA, FDMA, TDMA Aloha Adapive Aloha Backoff proocols Reservaion schemes Polling Disribued Compuing Group Mobile Compuing Summer 2003 Disribued Compuing

More information

Video streaming over Vajda Tamás

Video streaming over Vajda Tamás Video sreaming over 802.11 Vajda Tamás Video No all bis are creaed equal Group of Picures (GoP) Video Sequence Slice Macroblock Picure (Frame) Inra (I) frames, Prediced (P) Frames or Bidirecional (B) Frames.

More information

An efficient approach to improve throughput for TCP vegas in ad hoc network

An efficient approach to improve throughput for TCP vegas in ad hoc network Inernaional Research Journal of Engineering and Technology (IRJET) e-issn: 395-0056 Volume: 0 Issue: 03 June-05 www.irje.ne p-issn: 395-007 An efficien approach o improve hroughpu for TCP vegas in ad hoc

More information

! errors caused by signal attenuation, noise.!! receiver detects presence of errors:!

! errors caused by signal attenuation, noise.!! receiver detects presence of errors:! Daa Link Layer! The Daa Link layer can be furher subdivided ino:!.! Logical Link Conrol (LLC): error and flow conrol!.! Media Access Conrol (MAC): framing and media access! differen link proocols may provide

More information

Exercise 3: Bluetooth BR/EDR

Exercise 3: Bluetooth BR/EDR Wireless Communicaions, M. Rupf. Exercise 3: Blueooh BR/EDR Problem 1: Blueooh Daa Raes. Consider he ACL packe 3-DH5 wih a maximum user payload of 1021 byes. a) Deermine he maximum achievable daa rae in

More information

Evaluation and Improvement of Multicast Service in b

Evaluation and Improvement of Multicast Service in b Evaluaion and Improvemen of Mulicas Service in 802.11b Chrisian Bravo 1 and Agusín González 2 1 Universidad Federico Sana María, Deparmen of Elecronics. Valparaíso, Chile chbravo@elo.ufsm.cl 2 Universidad

More information

Network management and QoS provisioning - QoS in Frame Relay. . packet switching with virtual circuit service (virtual circuits are bidirectional);

Network management and QoS provisioning - QoS in Frame Relay. . packet switching with virtual circuit service (virtual circuits are bidirectional); QoS in Frame Relay Frame relay characerisics are:. packe swiching wih virual circui service (virual circuis are bidirecional);. labels are called DLCI (Daa Link Connecion Idenifier);. for connecion is

More information

Test - Accredited Configuration Engineer (ACE) Exam - PAN-OS 6.0 Version

Test - Accredited Configuration Engineer (ACE) Exam - PAN-OS 6.0 Version Tes - Accredied Configuraion Engineer (ACE) Exam - PAN-OS 6.0 Version ACE Exam Quesion 1 of 50. Which of he following saemens is NOT abou Palo Alo Neworks firewalls? Sysem defauls may be resored by performing

More information

Low-Cost WLAN based. Dr. Christian Hoene. Computer Science Department, University of Tübingen, Germany

Low-Cost WLAN based. Dr. Christian Hoene. Computer Science Department, University of Tübingen, Germany Low-Cos WLAN based Time-of-fligh fligh Trilaeraion Precision Indoor Personnel Locaion and Tracking for Emergency Responders Third Annual Technology Workshop, Augus 5, 2008 Worceser Polyechnic Insiue, Worceser,

More information

Scheduling. Scheduling. EDA421/DIT171 - Parallel and Distributed Real-Time Systems, Chalmers/GU, 2011/2012 Lecture #4 Updated March 16, 2012

Scheduling. Scheduling. EDA421/DIT171 - Parallel and Distributed Real-Time Systems, Chalmers/GU, 2011/2012 Lecture #4 Updated March 16, 2012 EDA421/DIT171 - Parallel and Disribued Real-Time Sysems, Chalmers/GU, 2011/2012 Lecure #4 Updaed March 16, 2012 Aemps o mee applicaion consrains should be done in a proacive way hrough scheduling. Schedule

More information

Page 1. Key Points from Last Lecture Frame format. EEC173B/ECS152C, Winter Wireless LANs

Page 1. Key Points from Last Lecture Frame format. EEC173B/ECS152C, Winter Wireless LANs EEC173/ECS152C, Winer 2006 Key Poins from Las Lecure Wireless LANs 802.11 Frame forma 802.11 MAC managemen Synchronizaion, Handoffs, Power MAC mehods: DCF & PCF CSMA/CA wih posiive ACK Exponenial backoff

More information

An Adaptive Spatial Depth Filter for 3D Rendering IP

An Adaptive Spatial Depth Filter for 3D Rendering IP JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE, VOL.3, NO. 4, DECEMBER, 23 175 An Adapive Spaial Deph Filer for 3D Rendering IP Chang-Hyo Yu and Lee-Sup Kim Absrac In his paper, we presen a new mehod

More information

Lecture 4. Programming with Message Passing: Applications and Performance

Lecture 4. Programming with Message Passing: Applications and Performance Lecure 4 Programming wih Message Passing: Applicaions and Performance Announcemens Quiz #1 in secion on 10/13 Miderm: evening of 10/30, 7:00 o 8:20 PM Wednesday s office hours sar a 1.30 (res of he quarer)

More information

User Adjustable Process Scheduling Mechanism for a Multiprocessor Embedded System

User Adjustable Process Scheduling Mechanism for a Multiprocessor Embedded System Proceedings of he 6h WSEAS Inernaional Conference on Applied Compuer Science, Tenerife, Canary Islands, Spain, December 16-18, 2006 346 User Adjusable Process Scheduling Mechanism for a Muliprocessor Embedded

More information

Using CANopen Slave Driver

Using CANopen Slave Driver CAN Bus User Manual Using CANopen Slave Driver V1. Table of Conens 1. SDO Communicaion... 1 2. PDO Communicaion... 1 3. TPDO Reading and RPDO Wriing... 2 4. RPDO Reading... 3 5. CANopen Communicaion Parameer

More information

CS422 Computer Networks

CS422 Computer Networks CS422 Compuer Neworks Lecure 2 Physical Layer Dr. Xiaobo Zhou Deparmen of Compuer Science CS422 PhysicalLayer.1 Quesions of Ineress How long will i ake o ransmi a message? How many bis are in he message

More information

Implementing Ray Casting in Tetrahedral Meshes with Programmable Graphics Hardware (Technical Report)

Implementing Ray Casting in Tetrahedral Meshes with Programmable Graphics Hardware (Technical Report) Implemening Ray Casing in Terahedral Meshes wih Programmable Graphics Hardware (Technical Repor) Marin Kraus, Thomas Erl March 28, 2002 1 Inroducion Alhough cell-projecion, e.g., [3, 2], and resampling,

More information

Delay in Packet Switched Networks

Delay in Packet Switched Networks 1 Delay in Packe Swiched Neworks Required reading: Kurose 1.5 and 1.6 CSE 4213, Fall 2006 Insrucor: N. Vlajic Delay in Packe-Swiched Neworks 2 Link/Nework Performance Measures: hroughpu and delay Link

More information

Design Alternatives for a Thin Lens Spatial Integrator Array

Design Alternatives for a Thin Lens Spatial Integrator Array Egyp. J. Solids, Vol. (7), No. (), (004) 75 Design Alernaives for a Thin Lens Spaial Inegraor Array Hala Kamal *, Daniel V azquez and Javier Alda and E. Bernabeu Opics Deparmen. Universiy Compluense of

More information

A time-space consistency solution for hardware-in-the-loop simulation system

A time-space consistency solution for hardware-in-the-loop simulation system Inernaional Conference on Advanced Elecronic Science and Technology (AEST 206) A ime-space consisency soluion for hardware-in-he-loop simulaion sysem Zexin Jiang a Elecric Power Research Insiue of Guangdong

More information

Sam knows that his MP3 player has 40% of its battery life left and that the battery charges by an additional 12 percentage points every 15 minutes.

Sam knows that his MP3 player has 40% of its battery life left and that the battery charges by an additional 12 percentage points every 15 minutes. 8.F Baery Charging Task Sam wans o ake his MP3 player and his video game player on a car rip. An hour before hey plan o leave, he realized ha he forgo o charge he baeries las nigh. A ha poin, he plugged

More information

Difficulty-aware Hybrid Search in Peer-to-Peer Networks

Difficulty-aware Hybrid Search in Peer-to-Peer Networks Difficuly-aware Hybrid Search in Peer-o-Peer Neworks Hanhua Chen, Hai Jin, Yunhao Liu, Lionel M. Ni School of Compuer Science and Technology Huazhong Univ. of Science and Technology {chenhanhua, hjin}@hus.edu.cn

More information

Shortest Path Algorithms. Lecture I: Shortest Path Algorithms. Example. Graphs and Matrices. Setting: Dr Kieran T. Herley.

Shortest Path Algorithms. Lecture I: Shortest Path Algorithms. Example. Graphs and Matrices. Setting: Dr Kieran T. Herley. Shores Pah Algorihms Background Seing: Lecure I: Shores Pah Algorihms Dr Kieran T. Herle Deparmen of Compuer Science Universi College Cork Ocober 201 direced graph, real edge weighs Le he lengh of a pah

More information

Mobile Computing IEEE Standard 9/10/14. CSE 40814/60814 Fall 2014

Mobile Computing IEEE Standard 9/10/14. CSE 40814/60814 Fall 2014 Mobile Compuing CSE 40814/60814 Fall 2014 IEEE IEEE (Ins4ue of Elecrical and Elecronics Engineers) esablished he 802.11 Group in 1990. Specifica4ons for sandard ra4fied in 1997. Ini4al speeds were 1 and

More information

STEREO PLANE MATCHING TECHNIQUE

STEREO PLANE MATCHING TECHNIQUE STEREO PLANE MATCHING TECHNIQUE Commission III KEY WORDS: Sereo Maching, Surface Modeling, Projecive Transformaion, Homography ABSTRACT: This paper presens a new ype of sereo maching algorihm called Sereo

More information

Packet Scheduling in a Low-Latency Optical Interconnect with Electronic Buffers

Packet Scheduling in a Low-Latency Optical Interconnect with Electronic Buffers Packe cheduling in a Low-Laency Opical Inerconnec wih Elecronic Buffers Lin Liu Zhenghao Zhang Yuanyuan Yang Dep Elecrical & Compuer Engineering Compuer cience Deparmen Dep Elecrical & Compuer Engineering

More information

LHP: An end-to-end reliable transport protocol over wireless data networks

LHP: An end-to-end reliable transport protocol over wireless data networks LHP: An end-o-end reliable ranspor proocol over wireless daa neworks Xia Gao, Suhas N. Diggavi, S. Muhukrishnan Absrac The nex generaion wireless neworks are posied o suppor large scale daa applicaions.

More information

/85/ $ IEEE

/85/ $ IEEE 174 Saged Circui Swiching MAURICIO ARANGO, HUSSEIN BADR, AND DAVID GELERNTER Absrac -Saged circui swiching (S) is a message-swiching echnique ha combines a new proocol wih new communicaion hardware. Proocol

More information

Web System for the Remote Control and Execution of an IEC Application

Web System for the Remote Control and Execution of an IEC Application Web Sysem for he Remoe Conrol and Execuion of an IEC 61499 Applicaion Oana ROHAT, Dan POPESCU Faculy of Auomaion and Compuer Science, Poliehnica Universiy, Splaiul Independenței 313, Bucureși, 060042,

More information

I. INTRODUCTION. Keywords -- Web Server, Perceived User Latency, HTTP, Local Measuring. interchangeably.

I. INTRODUCTION. Keywords -- Web Server, Perceived User Latency, HTTP, Local Measuring. interchangeably. Evaluaing Web User Perceived Laency Using Server Side Measuremens Marik Marshak 1 and Hanoch Levy School of Compuer Science Tel Aviv Universiy, Tel-Aviv, Israel mmarshak@emc.com, hanoch@pos.au.ac.il 1

More information

Location. Electrical. Loads. 2-wire mains-rated. 0.5 mm² to 1.5 mm² Max. length 300 m (with 1.5 mm² cable). Example: Belden 8471

Location. Electrical. Loads. 2-wire mains-rated. 0.5 mm² to 1.5 mm² Max. length 300 m (with 1.5 mm² cable). Example: Belden 8471 Produc Descripion Insallaion and User Guide Transiser Dimmer (454) The DIN rail mouned 454 is a 4channel ransisor dimmer. I can operae in one of wo modes; leading edge or railing edge. All 4 channels operae

More information

CS 152 Computer Architecture and Engineering. Lecture 7 - Memory Hierarchy-II

CS 152 Computer Architecture and Engineering. Lecture 7 - Memory Hierarchy-II CS 152 Compuer Archiecure and Engineering Lecure 7 - Memory Hierarchy-II Krse Asanovic Elecrical Engineering and Compuer Sciences Universiy of California a Berkeley hp://www.eecs.berkeley.edu/~krse hp://ins.eecs.berkeley.edu/~cs152

More information

Announcements. TCP Congestion Control. Goals of Today s Lecture. State Diagrams. TCP State Diagram

Announcements. TCP Congestion Control. Goals of Today s Lecture. State Diagrams. TCP State Diagram nnouncemens TCP Congesion Conrol Projec #3 should be ou onigh Can do individual or in a eam of 2 people Firs phase due November 16 - no slip days Exercise good (beer) ime managemen EE 122: Inro o Communicaion

More information

Improving the Efficiency of Dynamic Service Provisioning in Transport Networks with Scheduled Services

Improving the Efficiency of Dynamic Service Provisioning in Transport Networks with Scheduled Services Improving he Efficiency of Dynamic Service Provisioning in Transpor Neworks wih Scheduled Services Ralf Hülsermann, Monika Jäger and Andreas Gladisch Technologiezenrum, T-Sysems, Goslarer Ufer 35, D-1585

More information

A New Semantic Cache Management Method in Mobile Databases

A New Semantic Cache Management Method in Mobile Databases Journal o Compuer Science 1 (3): 351-354, 25 ISSN 1549-3636 Science Publicaions, 25 A New Semanic Cache Managemen Mehod in Mobile Daabases Shengei Shi, Jianzhong Li and Chaokun Wang School o Compuer Science

More information

A Matching Algorithm for Content-Based Image Retrieval

A Matching Algorithm for Content-Based Image Retrieval A Maching Algorihm for Conen-Based Image Rerieval Sue J. Cho Deparmen of Compuer Science Seoul Naional Universiy Seoul, Korea Absrac Conen-based image rerieval sysem rerieves an image from a daabase using

More information

Chapter 8 LOCATION SERVICES

Chapter 8 LOCATION SERVICES Disribued Compuing Group Chaper 8 LOCATION SERVICES Mobile Compuing Winer 2005 / 2006 Overview Mobile IP Moivaion Daa ransfer Encapsulaion Locaion Services & Rouing Classificaion of locaion services Home

More information

Wireless LANs: MAC. Wireless LAN: MAC. IEEE protocol stack. Module W.lan MAC

Wireless LANs: MAC. Wireless LAN: MAC. IEEE protocol stack. Module W.lan MAC Wireless LANs: W.lan.3-2 Wireless LAN: 802.11MAC Dr.M.Y.Wu@CSE Shanghai Jiaoong Universiy Shanghai, China Module W.lan.3 Dr.W.Shu@ECE Universiy of New Mexico Albuquerque, NM, USA managemen PANs & Blueooh:

More information

Image segmentation. Motivation. Objective. Definitions. A classification of segmentation techniques. Assumptions for thresholding

Image segmentation. Motivation. Objective. Definitions. A classification of segmentation techniques. Assumptions for thresholding Moivaion Image segmenaion Which pixels belong o he same objec in an image/video sequence? (spaial segmenaion) Which frames belong o he same video sho? (emporal segmenaion) Which frames belong o he same

More information

CS 152 Computer Architecture and Engineering. Lecture 6 - Memory

CS 152 Computer Architecture and Engineering. Lecture 6 - Memory CS 152 Compuer Archiecure and Engineering Lecure 6 - Memory Krse Asanovic Elecrical Engineering and Compuer Sciences Universiy of California a Berkeley hp://www.eecs.berkeley.edu/~krse hp://ins.eecs.berkeley.edu/~cs152

More information

Outline. EECS Components and Design Techniques for Digital Systems. Lec 06 Using FSMs Review: Typical Controller: state

Outline. EECS Components and Design Techniques for Digital Systems. Lec 06 Using FSMs Review: Typical Controller: state Ouline EECS 5 - Componens and Design Techniques for Digial Sysems Lec 6 Using FSMs 9-3-7 Review FSMs Mapping o FPGAs Typical uses of FSMs Synchronous Seq. Circuis safe composiion Timing FSMs in verilog

More information

Why not experiment with the system itself? Ways to study a system System. Application areas. Different kinds of systems

Why not experiment with the system itself? Ways to study a system System. Application areas. Different kinds of systems Simulaion Wha is simulaion? Simple synonym: imiaion We are ineresed in sudying a Insead of experimening wih he iself we experimen wih a model of he Experimen wih he Acual Ways o sudy a Sysem Experimen

More information

A Tool for Multi-Hour ATM Network Design considering Mixed Peer-to-Peer and Client-Server based Services

A Tool for Multi-Hour ATM Network Design considering Mixed Peer-to-Peer and Client-Server based Services A Tool for Muli-Hour ATM Nework Design considering Mied Peer-o-Peer and Clien-Server based Services Conac Auhor Name: Luis Cardoso Company / Organizaion: Porugal Telecom Inovação Complee Mailing Address:

More information

Improving Explicit Congestion Notification with the Mark-Front Strategy

Improving Explicit Congestion Notification with the Mark-Front Strategy Improving Explici Congesion Noificaion wih he Mark-Fron Sraegy Chunlei Liu Raj Jain Deparmen of Compuer and Informaion Science Chief Technology Officer, Nayna Neworks, Inc. The Ohio Sae Universiy, Columbus,

More information

This is the published version of a paper presented at The 2013 IEEE International Conference on Internet of Things, Beijing, China, August 2013.

This is the published version of a paper presented at The 2013 IEEE International Conference on Internet of Things, Beijing, China, August 2013. hp://www.diva-poral.org This is he published version of a paper presened a The 2013 IEEE Inernaional Conference on Inerne of Things, Beijing, China, 20-23 Augus 2013. Ciaion for he original published paper:

More information

IDEF3 Process Description Capture Method

IDEF3 Process Description Capture Method IDEF3 Process Descripion Capure Mehod IDEF3 is par of he IDEF family of mehods developmen funded by he US Air Force o provide modelling suppor for sysems engineering and enerprise inegraion 2 IDEF3 Mehod

More information

source managemen, naming, proecion, and service provisions. This paper concenraes on he basic processor scheduling aspecs of resource managemen. 2 The

source managemen, naming, proecion, and service provisions. This paper concenraes on he basic processor scheduling aspecs of resource managemen. 2 The Virual Compuers A New Paradigm for Disribued Operaing Sysems Banu Ozden y Aaron J. Goldberg Avi Silberschaz z 600 Mounain Ave. AT&T Bell Laboraories Murray Hill, NJ 07974 Absrac The virual compuers (VC)

More information

Performance Evaluation of Implementing Calls Prioritization with Different Queuing Disciplines in Mobile Wireless Networks

Performance Evaluation of Implementing Calls Prioritization with Different Queuing Disciplines in Mobile Wireless Networks Journal of Compuer Science 2 (5): 466-472, 2006 ISSN 1549-3636 2006 Science Publicaions Performance Evaluaion of Implemening Calls Prioriizaion wih Differen Queuing Disciplines in Mobile Wireless Neworks

More information

Po,,ll. I Appll I APP2 I I App3 I. Illll Illlllll II Illlll Illll Illll Illll Illll Illll Illll Illll Illll Illll Illll Illlll Illl Illl Illl

Po,,ll. I Appll I APP2 I I App3 I. Illll Illlllll II Illlll Illll Illll Illll Illll Illll Illll Illll Illll Illll Illll Illlll Illl Illl Illl Illll Illlllll II Illlll Illll Illll Illll Illll Illll Illll Illll Illll Illll Illll Illlll Illl Illl Illl US 20110153728A1 (19) nied Saes (12) Paen Applicaion Publicaion (10) Pub. No.: S 2011/0153728

More information

Delayed reservation decision in optical burst switching networks with optical buffers. Title. Li, GM; Li, VOK; Li, CY; Wai, PKA

Delayed reservation decision in optical burst switching networks with optical buffers. Title. Li, GM; Li, VOK; Li, CY; Wai, PKA Tile Delayed reservaion decision in opical burs swiching neworks wih opical buffers Auhor(s) Li, GM; Li, VOK; Li, CY; Wai, PKA Ciaion The 3rd nernaional Conference on Communicaions and Neworking in China

More information

Minimum cycle time analysis of Ethernet-based real-time protocols

Minimum cycle time analysis of Ethernet-based real-time protocols Minimum cycle ime analysis of Eherne-based real-ime proocols Jérémy Rober, Jean-Philippe Georges, Eric Rondeau, Thierry Divoux To cie his version: Jérémy Rober, Jean-Philippe Georges, Eric Rondeau, Thierry

More information

Overview of Board Revisions

Overview of Board Revisions s Sysem Overview MicroAuoBox Embedded PC MicroAuoBox II can be enhanced wih he MicroAuoBox Embedded PC. The MicroAuoBox EmbeddedPC is powered via he MicroAuoBox II power inpu connecor. Wih he common power

More information

NEWTON S SECOND LAW OF MOTION

NEWTON S SECOND LAW OF MOTION Course and Secion Dae Names NEWTON S SECOND LAW OF MOTION The acceleraion of an objec is defined as he rae of change of elociy. If he elociy changes by an amoun in a ime, hen he aerage acceleraion during

More information

Performance Characterisation of the MCNS DOCSIS 1.0 CATV Protocol with Prioritised First Come First Served Scheduling

Performance Characterisation of the MCNS DOCSIS 1.0 CATV Protocol with Prioritised First Come First Served Scheduling 1 Performance Characerisaion of he MCNS OCSIS 1.0 CTV Proocol wih Prioriised Firs Come Firs Served Scheduling V.Sdralia, C.Smyhe, P.Tzerefos, S.Cvekovic bsrac The Mulimedia Cable Neworks Sysems (MCNS)

More information

PLC Network Traffic Modeling for Implementation of Remote Monitoring of Electrical Power Consumption in Tanzania.

PLC Network Traffic Modeling for Implementation of Remote Monitoring of Electrical Power Consumption in Tanzania. PLC Nework Traffic Modeling for Implemenaion of Remoe Monioring of Elecrical Power Consumpion in Tanzania. Jusinian Anaory, Mussa M. Kissaka and Nerey H. Mvungi Faculy of Elecrical and Compuer Sysems Engineering

More information

Nonparametric CUSUM Charts for Process Variability

Nonparametric CUSUM Charts for Process Variability Journal of Academia and Indusrial Research (JAIR) Volume 3, Issue June 4 53 REEARCH ARTICLE IN: 78-53 Nonparameric CUUM Chars for Process Variabiliy D.M. Zombade and V.B. Ghue * Dep. of aisics, Walchand

More information

Modeling of IEEE in a Cluster of Synchronized Sensor Nodes

Modeling of IEEE in a Cluster of Synchronized Sensor Nodes Modeling of IEEE 802.15.4 in a Cluser of Synchronized Sensor Nodes Kenji Leibniz, Naoki Wakamiya, and Masayuki Muraa Graduae School of Informaion Science and Technology, Osaka Universiy, 1-5 Yamadaoka,

More information

An HTTP Web Traffic Model Based on the Top One Million Visited Web Pages

An HTTP Web Traffic Model Based on the Top One Million Visited Web Pages An HTTP Web Traffic Model Based on he Top One Million Visied Web Pages Rasin Pries, Zsol Magyari, Phuoc Tran-Gia Universiy of Würzburg, Insiue of Compuer Science, Germany Email: {pries,rangia}@informaik.uni-wuerzburg.de

More information

DCF/DSDMA: Enhanced DCF with SDMA Downlink Transmissions for WLANs

DCF/DSDMA: Enhanced DCF with SDMA Downlink Transmissions for WLANs DCF/DSDMA: Enhanced DCF wih SDMA Downlink Transmissions for WLANs Ruizhi Liao, oris ellala, Crisina Cano and Miquel Oliver NeTS Research Group Deparmen of Informaion and Communicaion Technologies Universia

More information

MATH Differential Equations September 15, 2008 Project 1, Fall 2008 Due: September 24, 2008

MATH Differential Equations September 15, 2008 Project 1, Fall 2008 Due: September 24, 2008 MATH 5 - Differenial Equaions Sepember 15, 8 Projec 1, Fall 8 Due: Sepember 4, 8 Lab 1.3 - Logisics Populaion Models wih Harvesing For his projec we consider lab 1.3 of Differenial Equaions pages 146 o

More information

Spline Curves. Color Interpolation. Normal Interpolation. Last Time? Today. glshademodel (GL_SMOOTH); Adjacency Data Structures. Mesh Simplification

Spline Curves. Color Interpolation. Normal Interpolation. Last Time? Today. glshademodel (GL_SMOOTH); Adjacency Data Structures. Mesh Simplification Las Time? Adjacency Daa Srucures Spline Curves Geomeric & opologic informaion Dynamic allocaion Efficiency of access Mesh Simplificaion edge collapse/verex spli geomorphs progressive ransmission view-dependen

More information

MB86297A Carmine Timing Analysis of the DDR Interface

MB86297A Carmine Timing Analysis of the DDR Interface Applicaion Noe MB86297A Carmine Timing Analysis of he DDR Inerface Fujisu Microelecronics Europe GmbH Hisory Dae Auhor Version Commen 05.02.2008 Anders Ramdahl 0.01 Firs draf 06.02.2008 Anders Ramdahl

More information

Real Time Integral-Based Structural Health Monitoring

Real Time Integral-Based Structural Health Monitoring Real Time Inegral-Based Srucural Healh Monioring The nd Inernaional Conference on Sensing Technology ICST 7 J. G. Chase, I. Singh-Leve, C. E. Hann, X. Chen Deparmen of Mechanical Engineering, Universiy

More information

An Improved Square-Root Nyquist Shaping Filter

An Improved Square-Root Nyquist Shaping Filter An Improved Square-Roo Nyquis Shaping Filer fred harris San Diego Sae Universiy fred.harris@sdsu.edu Sridhar Seshagiri San Diego Sae Universiy Seshigar.@engineering.sdsu.edu Chris Dick Xilinx Corp. chris.dick@xilinx.com

More information

An Experimental QoS Manager Implementation

An Experimental QoS Manager Implementation An Experimenal QoS Manager Implemenaion Drago Žagar, Goran Marinović, Slavko Rupčić Faculy of Elecrical Engineering Universiy of Osijek Kneza Trpimira 2B, Osijek Croaia drago.zagar@efos.hr Absrac-- Qualiy

More information

A MAC layer protocol for wireless networks with asymmetric links

A MAC layer protocol for wireless networks with asymmetric links A MAC layer proocol for wireless neworks wih asymmeric links Guoqiang Wang, Damla Turgu, Ladislau Bölöni, Yongchang Ji, Dan C. Marinescu School of Elecrical Engineering and Compuer Science, Universiy of

More information

SREM: A Novel Multicast Routing Algorithm - Comprehensive Cost Analysis

SREM: A Novel Multicast Routing Algorithm - Comprehensive Cost Analysis REM: A Novel Mulicas Rouing Algorihm - Comprehensive Cos Analysis Yewen Cao and Khalid Al-Begain chool of Compuing, Universiy of Glamorgan, CF37 DL, Wales, U.K E-mail:{ycao,kbegain}@glam.ac.uk Absrac Ever-increasing

More information

CS 152 Computer Architecture and Engineering. Lecture 6 - Memory

CS 152 Computer Architecture and Engineering. Lecture 6 - Memory CS 152 Compuer Archiecure and Engineering Lecure 6 - Memory Krse Asanovic Elecrical Engineering and Compuer Sciences Universiy of California a Berkeley hp://www.eecs.berkeley.edu/~krse hp://ins.eecs.berkeley.edu/~cs152

More information

EP2200 Queueing theory and teletraffic systems

EP2200 Queueing theory and teletraffic systems EP2200 Queueing heory and eleraffic sysems Vikoria Fodor Laboraory of Communicaion Neworks School of Elecrical Engineering Lecure 1 If you wan o model neworks Or a comple daa flow A queue's he key o help

More information

Dimmer time switch AlphaLux³ D / 27

Dimmer time switch AlphaLux³ D / 27 Dimmer ime swich AlphaLux³ D2 426 26 / 27! Safey noes This produc should be insalled in line wih insallaion rules, preferably by a qualified elecrician. Incorrec insallaion and use can lead o risk of elecric

More information

Accelerating Call Route Query of Multi-domain SIP System via P2P GONG Jing, SHEN Qing-guo, SHEN Huan-sheng

Accelerating Call Route Query of Multi-domain SIP System via P2P GONG Jing, SHEN Qing-guo, SHEN Huan-sheng 3rd Inernaional Conference on Mecharonics and Informaion Technology (ICMIT 2016) Acceleraing Call Roue Query of Muli-domain IP ysem via P2P GONG Jing, HEN Qing-guo, HEN Huan-sheng College of Communicaions

More information

1. Function 1. Push-button interface 4g.plus. Push-button interface 4-gang plus. 2. Installation. Table of Contents

1. Function 1. Push-button interface 4g.plus. Push-button interface 4-gang plus. 2. Installation. Table of Contents Chaper 4: Binary inpus 4.6 Push-buon inerfaces Push-buon inerface Ar. no. 6708xx Push-buon inerface 2-gang plus Push-buon inerfacechaper 4:Binary inpusar. no.6708xxversion 08/054.6Push-buon inerfaces.

More information

A NEW APPROACH FOR 3D MODELS TRANSMISSION

A NEW APPROACH FOR 3D MODELS TRANSMISSION A NEW APPROACH FOR 3D MODELS TRANSMISSION A. Guarnieri a, F. Piroi a, M. Ponin a, A. Veore a a CIRGEO, Inerdep. Research Cener of Carography, Phoogrammery, Remoe Sensing and GIS Universiy of Padova, Agripolis

More information

Opportunistic Flooding in Low-Duty-Cycle Wireless Sensor Networks with Unreliable Links

Opportunistic Flooding in Low-Duty-Cycle Wireless Sensor Networks with Unreliable Links 1 in Low-uy-ycle Wireless Sensor Neworks wih Unreliable Links Shuo uo, Suden Member, IEEE, Liang He, Member, IEEE, Yu u, Member, IEEE, o Jiang, Suden Member, IEEE, and Tian He, Member, IEEE bsrac looding

More information

Voltair Version 2.5 Release Notes (January, 2018)

Voltair Version 2.5 Release Notes (January, 2018) Volair Version 2.5 Release Noes (January, 2018) Inroducion 25-Seven s new Firmware Updae 2.5 for he Volair processor is par of our coninuing effors o improve Volair wih new feaures and capabiliies. For

More information

MOTION DETECTORS GRAPH MATCHING LAB PRE-LAB QUESTIONS

MOTION DETECTORS GRAPH MATCHING LAB PRE-LAB QUESTIONS NME: TE: LOK: MOTION ETETORS GRPH MTHING L PRE-L QUESTIONS 1. Read he insrucions, and answer he following quesions. Make sure you resae he quesion so I don hae o read he quesion o undersand he answer..

More information

Gauss-Jordan Algorithm

Gauss-Jordan Algorithm Gauss-Jordan Algorihm The Gauss-Jordan algorihm is a sep by sep procedure for solving a sysem of linear equaions which may conain any number of variables and any number of equaions. The algorihm is carried

More information

NRMI: Natural and Efficient Middleware

NRMI: Natural and Efficient Middleware NRMI: Naural and Efficien Middleware Eli Tilevich and Yannis Smaragdakis Cener for Experimenal Research in Compuer Sysems (CERCS), College of Compuing, Georgia Tech {ilevich, yannis}@cc.gaech.edu Absrac

More information

Automatic Calculation of Coverage Profiles for Coverage-based Testing

Automatic Calculation of Coverage Profiles for Coverage-based Testing Auomaic Calculaion of Coverage Profiles for Coverage-based Tesing Raimund Kirner 1 and Waler Haas 1 Vienna Universiy of Technology, Insiue of Compuer Engineering, Vienna, Ausria, raimund@vmars.uwien.ac.a

More information

EECS 487: Interactive Computer Graphics

EECS 487: Interactive Computer Graphics EECS 487: Ineracive Compuer Graphics Lecure 7: B-splines curves Raional Bézier and NURBS Cubic Splines A represenaion of cubic spline consiss of: four conrol poins (why four?) hese are compleely user specified

More information

Learning in Games via Opponent Strategy Estimation and Policy Search

Learning in Games via Opponent Strategy Estimation and Policy Search Learning in Games via Opponen Sraegy Esimaion and Policy Search Yavar Naddaf Deparmen of Compuer Science Universiy of Briish Columbia Vancouver, BC yavar@naddaf.name Nando de Freias (Supervisor) Deparmen

More information

Y. Tsiatouhas. VLSI Systems and Computer Architecture Lab

Y. Tsiatouhas. VLSI Systems and Computer Architecture Lab CMOS INEGRAED CIRCUI DESIGN ECHNIQUES Universiy of Ioannina Clocking Schemes Dep. of Compuer Science and Engineering Y. siaouhas CMOS Inegraed Circui Design echniques Overview 1. Jier Skew hroughpu Laency

More information

CAMERA CALIBRATION BY REGISTRATION STEREO RECONSTRUCTION TO 3D MODEL

CAMERA CALIBRATION BY REGISTRATION STEREO RECONSTRUCTION TO 3D MODEL CAMERA CALIBRATION BY REGISTRATION STEREO RECONSTRUCTION TO 3D MODEL Klečka Jan Docoral Degree Programme (1), FEEC BUT E-mail: xkleck01@sud.feec.vubr.cz Supervised by: Horák Karel E-mail: horak@feec.vubr.cz

More information

USBFC (USB Function Controller)

USBFC (USB Function Controller) USBFC () EIFUFAL501 User s Manual Doc #: 88-02-E01 Revision: 2.0 Dae: 03/24/98 (USBFC) 1. Highlighs... 4 1.1 Feaures... 4 1.2 Overview... 4 1.3 USBFC Block Diagram... 5 1.4 USBFC Typical Sysem Block Diagram...

More information

Communication Networks

Communication Networks Communicaion Neworks Chaper 10 Wireless Local Area Neworks According o IEEE 802.11 Communicaion Neworks: 10. IEEE 802.11 651 10. WLANs According o IEEE 802.11 Overview Organizaion of a WLAN according o

More information

MIC2569. Features. General Description. Applications. Typical Application. CableCARD Power Switch

MIC2569. Features. General Description. Applications. Typical Application. CableCARD Power Switch CableCARD Power Swich General Descripion is designed o supply power o OpenCable sysems and CableCARD hoss. These CableCARDs are also known as Poin of Disribuion (POD) cards. suppors boh Single and Muliple

More information

MoBAN: A Configurable Mobility Model for Wireless Body Area Networks

MoBAN: A Configurable Mobility Model for Wireless Body Area Networks MoBAN: A Configurable Mobiliy Model for Wireless Body Area Neworks Majid Nabi 1, Marc Geilen 1, Twan Basen 1,2 1 Deparmen of Elecrical Engineering, Eindhoven Universiy of Technology, he Neherlands 2 Embedded

More information

Analysis of Various Types of Bugs in the Object Oriented Java Script Language Coding

Analysis of Various Types of Bugs in the Object Oriented Java Script Language Coding Indian Journal of Science and Technology, Vol 8(21), DOI: 10.17485/ijs/2015/v8i21/69958, Sepember 2015 ISSN (Prin) : 0974-6846 ISSN (Online) : 0974-5645 Analysis of Various Types of Bugs in he Objec Oriened

More information

Utility-Based Hybrid Memory Management

Utility-Based Hybrid Memory Management Uiliy-Based Hybrid Memory Managemen Yang Li Saugaa Ghose Jongmoo Choi Jin Sun Hui Wang Onur Mulu Carnegie Mellon Universiy Dankook Universiy Beihang Universiy ETH Zürich While he memory fooprins of cloud

More information

ECO-friendly Distributed Routing Protocol for Reducing Network Energy Consumption

ECO-friendly Distributed Routing Protocol for Reducing Network Energy Consumption ECO-friendly Disribued Rouing Proocol for Reducing Nework Energy Consumpion Daisuke Arai and Kiyohio Yoshihara KDDI R&D Laboraories Inc. 2-1-15 Ohara Fujimino-shi Saiama, Japan Email: {di-arai, yosshy}@kddilabs.jp

More information